PREDICTING THE PERCEIVED SPACIOUSNESS OF STEREOPHONIC MUSIC RECORDINGS
|
|
- Georgina Eaton
- 6 years ago
- Views:
Transcription
1 PREDICTING THE PERCEIVED SPACIOUSNESS OF STEREOPHONIC MUSIC RECORDINGS Andy M. Sarroff and Juan P. Bello New York University ABSTRACT In a stereophonic music production, music producers seek to impart impressions of one or more virtual spaces upon the recording with two channels of audio. Our goal is to map spaciousness in stereophonic music to objective signal attributes. This is accomplished by building predictive functions by exemplar-based learning. First, spaciousness of recorded stereophonic music is parameterized by three discrete dimensions of perception the width of the source ensemble, the extent of reverberation, and the extent of immersion. A data set of 50 song excerpts is collected and annotated by humans for each dimension of spaciousness. A verbose feature set is generated on the music recordings and correlation-based feature selection is used to reduce the feature spaces. Exemplar-based support vector regression maps the feature sets to perceived spaciousness. We show that the predictive algorithms perform well on all dimensions and that perceived spaciousness can be successfully mapped to objective attributes of the audio signal. 1 INTRODUCTION Auditory spatial impression, or the concept of type and size of an actual or simulated space [1], helps a listener form judgements about auditory events and where those events occur. In natural acoustic settings, the relative positions of sound sources to each other, the relative positions of sound sources to a listener, the listener s and sources relative positions to the surfaces of the listening environment, and the physical composition of the structures that form and fill the listening environment are factors that contribute to spatial impression. In a stereophonic music production, music producers seek to impart impressions of one or more virtual spaces upon the recording with two channels of audio. Spatial cues are captured, manipulated, and added in order to provide the listener with impressions of simulated acoustic spaces, whether intentionally natural or unnatural sounding. The artful han- SMC 2009, July 23-25, Porto, Portugal Copyrights remain with the authors dling of these cues by producers can affect enjoyability of the listening experience. Our goal is to successfully predict the spatial impression that stereophonic recorded music imparts. A robust predictive system can empower music producers, listeners, and consumers with perceptually meaningful ways to evaluate, manipulate, and manage their music. Top-down controls for spaciousness may help music makers sculpt their sound. Casual listeners may customize their experience by using spaciousness controls similar to the EQ controls ubiquitous in consumer reproduction systems. By giving humans such resources, the music making and listening experience will become more flexible and interactive. We set about our task by parameterizing the concept of spaciousness with three dimensions. A data set of stereophonic music recordings is collected and subsequently annotated for each dimension of spaciousness. We then use exemplar-based learning to build functions that map objective measurements of digital audio to the annotated music recordings. We have structured this paper as follows: Section 2 gives some background as to how others have dealt with spaciousness and describes our approach to predicting spatial impression. In Section 3, we detail the processes of music selection and annotation. Section 4 describes the learning algorithms that are used and their parameterizations. The algorithms are tested and subsequent results are discussed in Section 5. We end with concluding remarks and suggestions for future work in Section 6. 2 BACKGROUND AND APPROACH Our approach is summarized in Figure 1. We begin with a set of musical recordings and end with three spatial dimensions, or target concepts the width of the source ensemble, the extent of reverberation, and the extent of immersion (defined in Table 1). Prediction is accomplished by mapping subjective ratings to objective measurements by machine learning. In this paper, we focus on three relations between listener and music the source relation (width of ensemble), the environment relation (reverberation), and the global relation (immersion). They have been selected from an amal-
2 The width of the source ensemble of a sound is how widely spread the ensemble of sound sources appears to be. The extent of reverberation of a sound is the overall impression of how apparent the reverberant field is. The extent of immersion is how much the sound appears to surround one s head. Table 1. Definitions of learning concepts. Figure 1. Framework for predicting perceived spaciousness of music recordings. gamation of perceived attributes found in literature on natural acoustics and sound capture/reproduction. For both of these areas, there is an implicit need to rate the spatial quality of such systems. To do so, researchers must know the dimensions of spaciousness that are most salient to human listeners and to have a means of evaluating spatial quality along these dimensions. In natural acoustics, spatial impression is divided into two primary dimensions, Apparent Source Width (ASW) and Listener Envelopment (LEV) [2, 3]. In sound capture and reproduction, the dimensionality of spaciousness is further demarcated. For example, [4] groups spatial attributes into descriptions that are related to sources, groups of sources, environments, and global scene parameters. We borrow from the literature of both fields for identifying salient spatial dimensions. ASW is defined as the apparent auditory width of the sound field created by a performing entity in [5] and ensemble width is the overall width of a defined group of sources in [4]. Both of these definitions connote one attribute that entails the width of the source ensemble. The extent of reverberation is directly linked to LEV in [5]. However, we use immersion to describe an attribute that encapsulates several kinds of envelopment, as is done in [4], and we treat immersion and reverberation independently, as is done in [6]. Once we have defined the spatial dimensions, or target concepts, we need a means of quantitatively evaluating them. In natural acoustics, objective measurements have been suggested numerous times, for example in [5] and [7]. Such measures quantify acoustic properties of physical space and relate these to perceived spaciousness. As recorded music only represents physical space virtually, measurements like these do not serve our goals. To the best of our knowledge, the perception of spatial attributes has been addressed qualitatively, but not quantitatively, in sound capture and reproduction. It is therefor necessary for us to newly construct a set of annotated music recordings and determine a quantitative relation. The target concepts cannot be divided into a semantically meaningful finite number of categories, so we impose a bounded arbitrary continuum and build a regression model for each concept. With the exception of listener experience, perceived attributes discussed in the literature are consistently related to sound sources or their environment, rather than personal properties like gender. These are universal in nature and therefor support a model which maps spaciousness to objective measurements of the recorded signal. 3 MUSIC SELECTION AND ANNOTATION 3.1 Music Selection and Segmentation Fifty songs were selected from an online music database [8]. The songs were equally distributed across seven genre groups: Alt/Punk, Classical, Electronic-Dance, Hip- Hop, R&B/Soul, and Rock/Pop. An equal propagation of chorus, verse, and bridge segments were spread across the pool. A seven second segment was excerpted from each of the songs. The duration was chosen, by informal evaluation, to be long enough to develop concrete impressions of spaciousness, yet short enough to prevent much temporal variation in spaciousness within the excerpt. None of the recordings were from commercially available songs; it is therefore unlikely that songs would be recognizable and induce bias during human annotation. 3.2 Labeling Human subject studies were conducted online and in a laboratory. In each, subjects were required to use headphones. First, basic demographic data was collected. Participants
3 were mostly experienced music listeners, but varied in country of residence, age, gender, profession, and other attributes of demography. Subjects were given explicit explanations and definitions of the dimensions that they were to evaluate. For each of the terms, participants were asked to listen to a non-musical mixture of sources (a room of applause). This training phase was designed to give participants time to familiarize themselves with the concepts and focus their listening on a simple stimulus. The nonmusical recordings exhibited the spatial dimensions but, to avoid pre-biasing their judgments of spaciousness, participants were not told how spacious the recordings were to be perceived. Subjects were asked to rate, on a bipolar 5-ordered Likert scale from Less to Neutral to More, each of the dimensions for each song. There were a total of 98 participants providing 2,523 total ratings. Ratings were transformed from a Likert space to a numerical space by assigning the 5-ordered response categories integer values. For each song and dimension, all responses that were at least 3 standard deviations from the mean were removed as outliers. Any participant who had more than two outliers for a dimension was removed from that dimension. The responses for each dimension were standardized to zero mean and unit variance, and the mean for each dimension and song was calculated. The pairwise correlation coefficient R was calculated between ratings for the learning concepts. Width immersion R was 0.87 and reverberation immersion R was Concepts width reverberation were the least correlated, with a coefficient of 0.32, suggesting that subjects perceived differences between these dimensions unambiguously. 4 MACHINE LEARNING A block diagram for building our objective-to-subjective mapping function is shown in Figure 2. At the beginning, we have a large feature space that objectively describes the music recordings. At the end, we have a support vector machine that needs optimization to accurately predict subjective ratings. In between, a correlation-based feature selection and subset voting scheme are used to narrow down the feature space. Then a grid search for the best parameterization of the support vector regression function is conducted. Each stage is described in detail below. Category Feature Dynamics RMS energy Rhythm Fluctuation Peak Position *, Fluctuation Peak Magnitude *, Fluctuation Spectral Centroid *, Tempo, Tempo Envelope Autocorrelation Peak Position, Tempo Envelope Autocorrelation Peak Magnitude, Attack Time, Attack Time Onset Curve Peak Position *, Attack Time Onset Peak Magnitude *, Attack Slope, Attack Slope Onset Curve Peak Position *, Attack Slope Onset Curve Peak Magnitude * Timbre Zero-Cross Rate, Spectral Centroid, Brightness, Spectral Spread, Spectral Skewness, Spectral Kurtosis, Roll- Off (95% threshold), Roll-Off (85% threshold), Spectral Entropy, Spectral Flatness, Roughness, Roughness Spectrum Peak Position, Roughness Spectrum Peak Magnitude, Spectral Irregularity, Irregularity Spectrum Peak Position, Irregularity Peak Magnitude, Inharmonicity, MFCCs, MFCCs, MFCCs, Low Energy *, Low Energy RMS, Spectral Flux Pitch Salient Pitch, Chromagram Peak Position, Chromagram Peak Magnitude, Chromagram Centroid, Key Clarity, Mode, Harmonic Change Detection Spatial Wideness Estimation *, Reverberation Estimation * Summary Functions Mean, Standard Deviation, Slope, Period Frequency, Period Amplitude, Period Entropy Table 2. List of audio features, their categories, and summary functions. Features with an asterisk ( * ) only had their mean calculated. The first blindly estimates, through magnitude cancellation techniques, how widely a mixture of sources is distributed within the stereo field. The second uses the residual of a linear predictor as an indicator of how much reverberation a signal contains. For most features, the recording was frame-decomposed and feature extraction was performed on each frame. Some features, such as Fluctuation, were calculated on the entire segment. The frame-level features were summarized by their mean and standard deviation. Additionally, their periodicity was estimated by autocorrelation, and period frequency, amplitude, and entropy was calculated. The size of the final feature space extracted from the recordings was 430 dimensions. The entire set of features, which can be sub-divided into categories of Dynamics, Rhythm, Timbre, Pitch, and Spatial, is listed in Table Feature Generation A verbose set of attributes was batch-generated on the Left- Right difference signal of the data set using the MIR Toolbox [9] and two additional features. The batch-generated features include many that are widely used, like MFCCs, Spectral Centroid, and Spectral Flatness. The two additional features, which we have reported in [10], are nonstandard but describe spatial characteristics of a signal. 4.2 Pre-Processing The feature space was normalized to the range [0, 1] and transformed into a principal components space. The nonprincipal components that accounted for the 5% least variance in the data set were discarded, and the data set was transformed back to its original symbolic attribute space.
4 FEATURE SPACE LEARNING CONCEPT CFS SUBSET SELECTION PARAMETER SEARCH SUPPORT VECTOR MACHINE Figure 2. Block diagram for building and optimizing the mapping function. 4.3 Feature Selection For each target concept, Correlation-Based Feature Selection (CFS) was performed with a greedy step-wise forward search heuristic. CFS chooses attributes that are well correlated to the learning target, yet exhibit low intercorrelation with each other. It has been shown to be good for filtering out irrelevant and redundant features [11]. However, supervised attribute selection can over-fit attributes to their learning concept when the same data set is used for training and testing [12]. To minimize subset selection bias, a percentile-based voting scheme with fold cross-validated attribute subset selection was performed. Multiple cross-validation (CV) is a robust way of estimating the predictive power of a machine when only a small data set is available. As each fold generated a different feature set, some features were selected more often than others. For each run, features were placed in a percentile bin based upon how many times that feature had been selected. Up to 11 new data sets with monotonically increasing feature spaces were generated in this way. Each feature space was then used to learn a non-optimized support vector regression algorithm for each dimension. The subset that performed the best for each learning concept was voted as the final subset for further system optimization and training. 4.4 Regression For each concept, a support vector regression model was implemented with the Sequential Minimal Optimization (SMO) algorithm [13]. Support vector machines have shown to generalize well to a number of classification and regression tasks. Our support vector models employed a polynomial kernel, K(x, y) = (< x, y > +1) p, chosen as the best in an informal kernel search. Support vector machines perform, to some extent, similarly well independent of kernel type if the kernel s parameters are well-chosen [14]. An exhaustive grid search for the optimal values of the support vector machine complexity (C) and its kernel exponent (p) was conducted after the optimal feature space had been selected. 5 EXPERIMENTS AND RESULTS For each dimension of spaciousness, the best feature space was found by using Multiple CV. Then we systematically searched for the support vector parameterization that yielded the lowest error for each concept. Success was evaluated by relative absolute error (RAE), which is insensitive to scale. RAE is the sum of all the errors normalized by the sum of the errors of a baseline prediction function, Zero-R. Zero-R picks the mean value of the test fold for every instance. An error of 0% would denote perfect prediction. Figure 3 shows the results of testing for the best feature space percentile. All predictors show two local minima: Width at the 20 th and 50 th percentiles; reverberation at the 10 th and 40 th percentiles; and immersion at the 20 th and 70 th percentiles. This indicates that there might have been more than one optimal feature subset percentile to use. We have chosen the percentile that yielded the lowest RAE for the algorithm, without testing all local minima. The steepness of the error curves between the 0 and 10 th percentiles shows that simply using the entire feature set without any feature selection would greatly inhibit the performance of the support vector algorithm. The final test results are depicted in Table 3. The mean absolute error (MAE), which is dependent on scale, was no more than 0.11 for any of the predictors. The average MAE for the Zero-R predictor is shown for comparison at the bottom of the table. The predictive capability of each of the machines was well above chance, as indicated by the RAE. All predictors had a correlation coefficient R of 0.73 or higher. An R value of 0.0 would denote a complete lack of correlation between the predicted and actual values. The predictor for wideness of source ensemble performed the poorest, but still well above chance. By all measurements of accuracy, the predictor for extent of reverberation performed the best.
5 RAR (%) Performance By Feature Space Percentile Width Rev. Imm Percentile Figure 3. Performance of non-optimized machine on monotonically decreasing feature spaces. Its coefficient of determination (R 2 ) indicates that the function accounted for 62% of the variance in the test set. A summary of the final feature subset percentile used for learning each concept is shown in Table 4. While most features are probably not individually useful, the correct combination of features is. Features that were selected for more than one learning concept are shown in boldface. The width and immersion dimensions shared the most features in common; this is understandable, as these dimensions shared the highest correlation among annotations. Selected features for all three concepts were largely from the Timbre category. We find it interesting that the reverberation predictor picked three features from the Pitch category. We also note that the spatial estimators for wideness and reverberation were automatically chosen for the tasks of predicting source ensemble wideness and extent of immersion. The error surfaces for parameterizations of each of the machines is shown in Figure 4. These surfaces show the RAE for each value in our grid search for optimal C and p values. It can be seen that the surfaces are not flat and that a globally optimal parameterization can be found for each. Yet they depict few local minima and are relatively smooth, suggesting that other parameter choices in between the grid Width Rev. Imm. RAE(%) MAE R R MAE (Zero-R) Table 3. The final mean absolute error (MAE), relative absolute error (RAE), correlation coefficient (R), and coefficient of determination (R 2 ) of the learning machines are given. The MAE for a baseline regression function, Zero- R, is given for comparison. All results are averaged from Multiple CV. Concept (%-tile) Width (50 %) Reverb. (40 %) Imm. (20 %) Features Tempo Envelope Autocorrelation Peak Magnitude Period Frequency, Spectral Flatness Period Amplitude, Wideness Estimation Mean, Reverb Estimation Mean, MFCC Slope 5, MFCC Mean 11 MFCC Mean 3, MFCC Period Entropy 3, MFCC Slope 3, MFCC Period Amplitude 13, Key Clarity Slope, Chromagram Peak Magnitude Period Frequency, Harmonic Change Detection Function Period Amplitude, Spectral Flux Period Amplitude, Pitch Period Amplitude, MFCC Slope 10, MFCC Period Frequency 10, MFCC Slope 13 MFCC Period Entropy 6, Spectral Centroid Period Entropy, Tempo Envelope Autocorrelation Peak Magnitude Period Frequency, Spectral Flatness Period Amplitude, Spectral Kurtosis Standard Deviation, Wideness Estimation Mean, Reverb Estimation Mean, Mode Period Entropy, Pitch Period Frequency, MFCC Slope 7, MFCC Slope 5, MFCC Slope 11, MFCC Mean 11, MFCC Mean 11 Table 4. Selected feature spaces after running on nonoptimized machine. Features in boldface were picked for more than one learning concept. marks would not have significantly improved results. It is worth noting that the flattest error surface, that for extent of reverberation, is also the one that performed the best, indicating robustness against parameter choices. 6 CONCLUSIONS AND FUTURE WORK We have presented a model for the automatic prediction of spaciousness in stereophonic music. We first parameterized the concept of spaciousness with the dimensions of source ensemble width, extent of reverberation, and extent of immersion. A verbose feature space of objective measurements was generated on a data set of human-annoted music recordings. Feature subset selection by percentile voting was used to narrow the feature space. The three target concepts were effectively learned by support vector regression with a polynomial basis function, achieving a direct mapping between signal attribute and subjective perception. Prediction for the extent of reverberation performed the best, while predictions for the wideness of the ensemble source and the extent of immersion performed slightly poorer relative to reverberation. All concept predictions exhibited RAE much better than chance. This work is based on an assumption of independence between the learning concepts. Future work will include deeper examination of dimensional interdependency, exploration of other regressors, kernels, and feature selection algorithms, and increasing the size of our database. The accuracies of the models suggest that objective measurements of digital audio can be successfully mapped to new dimensions of music perception. Such mappings may
6 Width [2] W. Keet, The influence of early lateral reflections on the spatial impression, in 6th International Congress on Acoustics, Tokyo, E-2-4, RAE (%) p C Reverberation [3] M. Barron, Late lateral energy fractions and the envelopment question in concert halls, Applied Acoustics, vol. 62, no. 2, pp , [4] F. Rumsey, Spatial quality evaluation for reproduced sound: Terminology, meaning, and a scene-based paradigm, Journal of the Audio Engineering Society, vol. 50, no. 9, pp , RAE (%) RAE (%) p C Immersion p C Figure 4. Relative absolute error surface for machine parameter grid search of kernel exponent p and machine complexity C. allow music producers to have more control over their domain, including feature-driven audio synthesis and perceptually meaningful sound-sculpting. In addition, this work examines signal properties and perceptual attributes that can be tied directly to studio production of recorded music. Spaciousness is manipulated by the music engineer by applying a number of recording and signal processing techniques. By directly mapping signal attributes to the perceptual domain, music producers may gain new resources for their trade. We believe that the perceptual components of music listening that are affected by processes that occur in the production studio are a rich, yet under-exploited information stream to harvest. 7 REFERENCES [1] J. Blauert and W. Lindemann, Auditory spaciousness - some further psychoacoustic analyses, Journal of the Acoustical Society of America, vol., no. 2, pp , Aug [5] T. Okano, L. L. Beranek, and T. Hidaka, Relations among interaural cross-correlation coefficient (iacc(e)), lateral fraction (lfe), and apparent source width (asw) in concert halls, Journal of the Acoustical Society of America, vol. 104, no. 1, pp , Jul [6] J. Berg and F. Rumsey, Systematic evaluation of perceived spatial quality, in Proceedings of AES 24th International Conference on Multichannel Audio, Banff, Alberta, Canada, [Online]. Available: [7] T. Hanyu and S. Kimura, A new objective measure for evaluation of listener envelopment focusing on the spatial balance of reflections, APPLIED ACOUSTICS, vol. 62, no. 2, pp , Feb [8] Mp3 music downloads. [Online]. Available: http: // [9] O. Lartillot, P. Toiviainen, and T. Eerola. (2008) Mirtoolbox. [Online]. Available: music/coe/materials/mirtoolbox [10] A. Sarroff and J. Bello, Measurements of spaciousness for stereophonic music, in 125th Convention of the Audio Engineering Society, San Francisco, USA. October, 2008, [11] M. Hall, Correlation-based feature selection for machine learning, Ph.D. dissertation, University of Waikato, Department of Computer Science, Hamilton, New Zealand, April [12] A. J. Miller, Subset Selection in Regression. CRC Press, [13] J. Smola, Alex and B. Schölkopf, A tutorial on support vector regression, Statistics and Computing, vol. 14, no. 3, pp , [14] B. Scholkopf and J. Smola, Alexander, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. Cambridge, MA, USA: MIT Press, 2001.
MUSI-6201 Computational Music Analysis
MUSI-6201 Computational Music Analysis Part 9.1: Genre Classification alexander lerch November 4, 2015 temporal analysis overview text book Chapter 8: Musical Genre, Similarity, and Mood (pp. 151 155)
More informationSPACIOUSNESS IN RECORDED MUSIC: HUMAN PERCEPTION, OBJECTIVE MEASUREMENT, AND MACHINE PREDICTION. Andy M. Sarroff
SPACIOUSNESS IN RECORDED MUSIC: HUMAN PERCEPTION, OBJECTIVE MEASUREMENT, AND MACHINE PREDICTION Andy M. Sarroff Submitted in partial fulfillment of the requirements for the Master of Music in Music Technology
More informationTempo and Beat Analysis
Advanced Course Computer Science Music Processing Summer Term 2010 Meinard Müller, Peter Grosche Saarland University and MPI Informatik meinard@mpi-inf.mpg.de Tempo and Beat Analysis Musical Properties:
More informationSubjective Similarity of Music: Data Collection for Individuality Analysis
Subjective Similarity of Music: Data Collection for Individuality Analysis Shota Kawabuchi and Chiyomi Miyajima and Norihide Kitaoka and Kazuya Takeda Nagoya University, Nagoya, Japan E-mail: shota.kawabuchi@g.sp.m.is.nagoya-u.ac.jp
More informationInstrument Recognition in Polyphonic Mixtures Using Spectral Envelopes
Instrument Recognition in Polyphonic Mixtures Using Spectral Envelopes hello Jay Biernat Third author University of Rochester University of Rochester Affiliation3 words jbiernat@ur.rochester.edu author3@ismir.edu
More informationTopics in Computer Music Instrument Identification. Ioanna Karydi
Topics in Computer Music Instrument Identification Ioanna Karydi Presentation overview What is instrument identification? Sound attributes & Timbre Human performance The ideal algorithm Selected approaches
More informationTOWARDS IMPROVING ONSET DETECTION ACCURACY IN NON- PERCUSSIVE SOUNDS USING MULTIMODAL FUSION
TOWARDS IMPROVING ONSET DETECTION ACCURACY IN NON- PERCUSSIVE SOUNDS USING MULTIMODAL FUSION Jordan Hochenbaum 1,2 New Zealand School of Music 1 PO Box 2332 Wellington 6140, New Zealand hochenjord@myvuw.ac.nz
More informationAutomatic Construction of Synthetic Musical Instruments and Performers
Ph.D. Thesis Proposal Automatic Construction of Synthetic Musical Instruments and Performers Ning Hu Carnegie Mellon University Thesis Committee Roger B. Dannenberg, Chair Michael S. Lewicki Richard M.
More informationLOUDNESS EFFECT OF THE DIFFERENT TONES ON THE TIMBRE SUBJECTIVE PERCEPTION EXPERIMENT OF ERHU
The 21 st International Congress on Sound and Vibration 13-17 July, 2014, Beijing/China LOUDNESS EFFECT OF THE DIFFERENT TONES ON THE TIMBRE SUBJECTIVE PERCEPTION EXPERIMENT OF ERHU Siyu Zhu, Peifeng Ji,
More informationAutomatic Laughter Detection
Automatic Laughter Detection Mary Knox Final Project (EECS 94) knoxm@eecs.berkeley.edu December 1, 006 1 Introduction Laughter is a powerful cue in communication. It communicates to listeners the emotional
More informationPerceptual dimensions of short audio clips and corresponding timbre features
Perceptual dimensions of short audio clips and corresponding timbre features Jason Musil, Budr El-Nusairi, Daniel Müllensiefen Department of Psychology, Goldsmiths, University of London Question How do
More informationSupervised Learning in Genre Classification
Supervised Learning in Genre Classification Introduction & Motivation Mohit Rajani and Luke Ekkizogloy {i.mohit,luke.ekkizogloy}@gmail.com Stanford University, CS229: Machine Learning, 2009 Now that music
More informationMODELING RHYTHM SIMILARITY FOR ELECTRONIC DANCE MUSIC
MODELING RHYTHM SIMILARITY FOR ELECTRONIC DANCE MUSIC Maria Panteli University of Amsterdam, Amsterdam, Netherlands m.x.panteli@gmail.com Niels Bogaards Elephantcandy, Amsterdam, Netherlands niels@elephantcandy.com
More informationAnalysis, Synthesis, and Perception of Musical Sounds
Analysis, Synthesis, and Perception of Musical Sounds The Sound of Music James W. Beauchamp Editor University of Illinois at Urbana, USA 4y Springer Contents Preface Acknowledgments vii xv 1. Analysis
More informationMusic Complexity Descriptors. Matt Stabile June 6 th, 2008
Music Complexity Descriptors Matt Stabile June 6 th, 2008 Musical Complexity as a Semantic Descriptor Modern digital audio collections need new criteria for categorization and searching. Applicable to:
More informationImproving Frame Based Automatic Laughter Detection
Improving Frame Based Automatic Laughter Detection Mary Knox EE225D Class Project knoxm@eecs.berkeley.edu December 13, 2007 Abstract Laughter recognition is an underexplored area of research. My goal for
More informationPitch Perception and Grouping. HST.723 Neural Coding and Perception of Sound
Pitch Perception and Grouping HST.723 Neural Coding and Perception of Sound Pitch Perception. I. Pure Tones The pitch of a pure tone is strongly related to the tone s frequency, although there are small
More informationAUTOREGRESSIVE MFCC MODELS FOR GENRE CLASSIFICATION IMPROVED BY HARMONIC-PERCUSSION SEPARATION
AUTOREGRESSIVE MFCC MODELS FOR GENRE CLASSIFICATION IMPROVED BY HARMONIC-PERCUSSION SEPARATION Halfdan Rump, Shigeki Miyabe, Emiru Tsunoo, Nobukata Ono, Shigeki Sagama The University of Tokyo, Graduate
More informationThe Research of Controlling Loudness in the Timbre Subjective Perception Experiment of Sheng
The Research of Controlling Loudness in the Timbre Subjective Perception Experiment of Sheng S. Zhu, P. Ji, W. Kuang and J. Yang Institute of Acoustics, CAS, O.21, Bei-Si-huan-Xi Road, 100190 Beijing,
More informationTYING SEMANTIC LABELS TO COMPUTATIONAL DESCRIPTORS OF SIMILAR TIMBRES
TYING SEMANTIC LABELS TO COMPUTATIONAL DESCRIPTORS OF SIMILAR TIMBRES Rosemary A. Fitzgerald Department of Music Lancaster University, Lancaster, LA1 4YW, UK r.a.fitzgerald@lancaster.ac.uk ABSTRACT This
More informationMusic Alignment and Applications. Introduction
Music Alignment and Applications Roger B. Dannenberg Schools of Computer Science, Art, and Music Introduction Music information comes in many forms Digital Audio Multi-track Audio Music Notation MIDI Structured
More informationDAY 1. Intelligent Audio Systems: A review of the foundations and applications of semantic audio analysis and music information retrieval
DAY 1 Intelligent Audio Systems: A review of the foundations and applications of semantic audio analysis and music information retrieval Jay LeBoeuf Imagine Research jay{at}imagine-research.com Rebecca
More informationMeasurement of overtone frequencies of a toy piano and perception of its pitch
Measurement of overtone frequencies of a toy piano and perception of its pitch PACS: 43.75.Mn ABSTRACT Akira Nishimura Department of Media and Cultural Studies, Tokyo University of Information Sciences,
More informationRobert Alexandru Dobre, Cristian Negrescu
ECAI 2016 - International Conference 8th Edition Electronics, Computers and Artificial Intelligence 30 June -02 July, 2016, Ploiesti, ROMÂNIA Automatic Music Transcription Software Based on Constant Q
More informationGCT535- Sound Technology for Multimedia Timbre Analysis. Graduate School of Culture Technology KAIST Juhan Nam
GCT535- Sound Technology for Multimedia Timbre Analysis Graduate School of Culture Technology KAIST Juhan Nam 1 Outlines Timbre Analysis Definition of Timbre Timbre Features Zero-crossing rate Spectral
More informationRecognising Cello Performers Using Timbre Models
Recognising Cello Performers Using Timbre Models Magdalena Chudy and Simon Dixon Abstract In this paper, we compare timbre features of various cello performers playing the same instrument in solo cello
More informationABSOLUTE OR RELATIVE? A NEW APPROACH TO BUILDING FEATURE VECTORS FOR EMOTION TRACKING IN MUSIC
ABSOLUTE OR RELATIVE? A NEW APPROACH TO BUILDING FEATURE VECTORS FOR EMOTION TRACKING IN MUSIC Vaiva Imbrasaitė, Peter Robinson Computer Laboratory, University of Cambridge, UK Vaiva.Imbrasaite@cl.cam.ac.uk
More informationAutomatic music transcription
Music transcription 1 Music transcription 2 Automatic music transcription Sources: * Klapuri, Introduction to music transcription, 2006. www.cs.tut.fi/sgn/arg/klap/amt-intro.pdf * Klapuri, Eronen, Astola:
More informationHowever, in studies of expressive timing, the aim is to investigate production rather than perception of timing, that is, independently of the listene
Beat Extraction from Expressive Musical Performances Simon Dixon, Werner Goebl and Emilios Cambouropoulos Austrian Research Institute for Artificial Intelligence, Schottengasse 3, A-1010 Vienna, Austria.
More informationTOWARD UNDERSTANDING EXPRESSIVE PERCUSSION THROUGH CONTENT BASED ANALYSIS
TOWARD UNDERSTANDING EXPRESSIVE PERCUSSION THROUGH CONTENT BASED ANALYSIS Matthew Prockup, Erik M. Schmidt, Jeffrey Scott, and Youngmoo E. Kim Music and Entertainment Technology Laboratory (MET-lab) Electrical
More informationPOST-PROCESSING FIDDLE : A REAL-TIME MULTI-PITCH TRACKING TECHNIQUE USING HARMONIC PARTIAL SUBTRACTION FOR USE WITHIN LIVE PERFORMANCE SYSTEMS
POST-PROCESSING FIDDLE : A REAL-TIME MULTI-PITCH TRACKING TECHNIQUE USING HARMONIC PARTIAL SUBTRACTION FOR USE WITHIN LIVE PERFORMANCE SYSTEMS Andrew N. Robertson, Mark D. Plumbley Centre for Digital Music
More informationONLINE ACTIVITIES FOR MUSIC INFORMATION AND ACOUSTICS EDUCATION AND PSYCHOACOUSTIC DATA COLLECTION
ONLINE ACTIVITIES FOR MUSIC INFORMATION AND ACOUSTICS EDUCATION AND PSYCHOACOUSTIC DATA COLLECTION Travis M. Doll Ray V. Migneco Youngmoo E. Kim Drexel University, Electrical & Computer Engineering {tmd47,rm443,ykim}@drexel.edu
More informationComputational Models of Music Similarity. Elias Pampalk National Institute for Advanced Industrial Science and Technology (AIST)
Computational Models of Music Similarity 1 Elias Pampalk National Institute for Advanced Industrial Science and Technology (AIST) Abstract The perceived similarity of two pieces of music is multi-dimensional,
More informationMusic Genre Classification and Variance Comparison on Number of Genres
Music Genre Classification and Variance Comparison on Number of Genres Miguel Francisco, miguelf@stanford.edu Dong Myung Kim, dmk8265@stanford.edu 1 Abstract In this project we apply machine learning techniques
More informationWHAT MAKES FOR A HIT POP SONG? WHAT MAKES FOR A POP SONG?
WHAT MAKES FOR A HIT POP SONG? WHAT MAKES FOR A POP SONG? NICHOLAS BORG AND GEORGE HOKKANEN Abstract. The possibility of a hit song prediction algorithm is both academically interesting and industry motivated.
More informationCS229 Project Report Polyphonic Piano Transcription
CS229 Project Report Polyphonic Piano Transcription Mohammad Sadegh Ebrahimi Stanford University Jean-Baptiste Boin Stanford University sadegh@stanford.edu jbboin@stanford.edu 1. Introduction In this project
More informationProceedings of Meetings on Acoustics
Proceedings of Meetings on Acoustics Volume 19, 2013 http://acousticalsociety.org/ ICA 2013 Montreal Montreal, Canada 2-7 June 2013 Musical Acoustics Session 3pMU: Perception and Orchestration Practice
More informationSYNTHESIS FROM MUSICAL INSTRUMENT CHARACTER MAPS
Published by Institute of Electrical Engineers (IEE). 1998 IEE, Paul Masri, Nishan Canagarajah Colloquium on "Audio and Music Technology"; November 1998, London. Digest No. 98/470 SYNTHESIS FROM MUSICAL
More informationAudio Feature Extraction for Corpus Analysis
Audio Feature Extraction for Corpus Analysis Anja Volk Sound and Music Technology 5 Dec 2017 1 Corpus analysis What is corpus analysis study a large corpus of music for gaining insights on general trends
More informationNeural Network for Music Instrument Identi cation
Neural Network for Music Instrument Identi cation Zhiwen Zhang(MSE), Hanze Tu(CCRMA), Yuan Li(CCRMA) SUN ID: zhiwen, hanze, yuanli92 Abstract - In the context of music, instrument identi cation would contribute
More informationMusic Emotion Recognition. Jaesung Lee. Chung-Ang University
Music Emotion Recognition Jaesung Lee Chung-Ang University Introduction Searching Music in Music Information Retrieval Some information about target music is available Query by Text: Title, Artist, or
More informationClassification of Timbre Similarity
Classification of Timbre Similarity Corey Kereliuk McGill University March 15, 2007 1 / 16 1 Definition of Timbre What Timbre is Not What Timbre is A 2-dimensional Timbre Space 2 3 Considerations Common
More information10 Visualization of Tonal Content in the Symbolic and Audio Domains
10 Visualization of Tonal Content in the Symbolic and Audio Domains Petri Toiviainen Department of Music PO Box 35 (M) 40014 University of Jyväskylä Finland ptoiviai@campus.jyu.fi Abstract Various computational
More informationA Beat Tracking System for Audio Signals
A Beat Tracking System for Audio Signals Simon Dixon Austrian Research Institute for Artificial Intelligence, Schottengasse 3, A-1010 Vienna, Austria. simon@ai.univie.ac.at April 7, 2000 Abstract We present
More information19 th INTERNATIONAL CONGRESS ON ACOUSTICS MADRID, 2-7 SEPTEMBER 2007
19 th INTERNATIONAL CONGRESS ON ACOUSTICS MADRID, 2-7 SEPTEMBER 2007 AN HMM BASED INVESTIGATION OF DIFFERENCES BETWEEN MUSICAL INSTRUMENTS OF THE SAME TYPE PACS: 43.75.-z Eichner, Matthias; Wolff, Matthias;
More informationRecognising Cello Performers using Timbre Models
Recognising Cello Performers using Timbre Models Chudy, Magdalena; Dixon, Simon For additional information about this publication click this link. http://qmro.qmul.ac.uk/jspui/handle/123456789/5013 Information
More informationTimbre blending of wind instruments: acoustics and perception
Timbre blending of wind instruments: acoustics and perception Sven-Amin Lembke CIRMMT / Music Technology Schulich School of Music, McGill University sven-amin.lembke@mail.mcgill.ca ABSTRACT The acoustical
More informationTopic 10. Multi-pitch Analysis
Topic 10 Multi-pitch Analysis What is pitch? Common elements of music are pitch, rhythm, dynamics, and the sonic qualities of timbre and texture. An auditory perceptual attribute in terms of which sounds
More informationReal-time Granular Sampling Using the IRCAM Signal Processing Workstation. Cort Lippe IRCAM, 31 rue St-Merri, Paris, 75004, France
Cort Lippe 1 Real-time Granular Sampling Using the IRCAM Signal Processing Workstation Cort Lippe IRCAM, 31 rue St-Merri, Paris, 75004, France Running Title: Real-time Granular Sampling [This copy of this
More information2. AN INTROSPECTION OF THE MORPHING PROCESS
1. INTRODUCTION Voice morphing means the transition of one speech signal into another. Like image morphing, speech morphing aims to preserve the shared characteristics of the starting and final signals,
More informationDrum Sound Identification for Polyphonic Music Using Template Adaptation and Matching Methods
Drum Sound Identification for Polyphonic Music Using Template Adaptation and Matching Methods Kazuyoshi Yoshii, Masataka Goto and Hiroshi G. Okuno Department of Intelligence Science and Technology National
More informationModeling memory for melodies
Modeling memory for melodies Daniel Müllensiefen 1 and Christian Hennig 2 1 Musikwissenschaftliches Institut, Universität Hamburg, 20354 Hamburg, Germany 2 Department of Statistical Science, University
More informationTempo and Beat Tracking
Tutorial Automatisierte Methoden der Musikverarbeitung 47. Jahrestagung der Gesellschaft für Informatik Tempo and Beat Tracking Meinard Müller, Christof Weiss, Stefan Balke International Audio Laboratories
More informationTranscription of the Singing Melody in Polyphonic Music
Transcription of the Singing Melody in Polyphonic Music Matti Ryynänen and Anssi Klapuri Institute of Signal Processing, Tampere University Of Technology P.O.Box 553, FI-33101 Tampere, Finland {matti.ryynanen,
More informationFeatures for Audio and Music Classification
Features for Audio and Music Classification Martin F. McKinney and Jeroen Breebaart Auditory and Multisensory Perception, Digital Signal Processing Group Philips Research Laboratories Eindhoven, The Netherlands
More informationAnalytic Comparison of Audio Feature Sets using Self-Organising Maps
Analytic Comparison of Audio Feature Sets using Self-Organising Maps Rudolf Mayer, Jakob Frank, Andreas Rauber Institute of Software Technology and Interactive Systems Vienna University of Technology,
More informationMASTER'S THESIS. Listener Envelopment
MASTER'S THESIS 2008:095 Listener Envelopment Effects of changing the sidewall material in a model of an existing concert hall Dan Nyberg Luleå University of Technology Master thesis Audio Technology Department
More informationAutomatic Extraction of Popular Music Ringtones Based on Music Structure Analysis
Automatic Extraction of Popular Music Ringtones Based on Music Structure Analysis Fengyan Wu fengyanyy@163.com Shutao Sun stsun@cuc.edu.cn Weiyao Xue Wyxue_std@163.com Abstract Automatic extraction of
More informationTHE importance of music content analysis for musical
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 15, NO. 1, JANUARY 2007 333 Drum Sound Recognition for Polyphonic Audio Signals by Adaptation and Matching of Spectrogram Templates With
More informationAN APPROACH FOR MELODY EXTRACTION FROM POLYPHONIC AUDIO: USING PERCEPTUAL PRINCIPLES AND MELODIC SMOOTHNESS
AN APPROACH FOR MELODY EXTRACTION FROM POLYPHONIC AUDIO: USING PERCEPTUAL PRINCIPLES AND MELODIC SMOOTHNESS Rui Pedro Paiva CISUC Centre for Informatics and Systems of the University of Coimbra Department
More informationReconstruction of Ca 2+ dynamics from low frame rate Ca 2+ imaging data CS229 final project. Submitted by: Limor Bursztyn
Reconstruction of Ca 2+ dynamics from low frame rate Ca 2+ imaging data CS229 final project. Submitted by: Limor Bursztyn Introduction Active neurons communicate by action potential firing (spikes), accompanied
More informationSkip Length and Inter-Starvation Distance as a Combined Metric to Assess the Quality of Transmitted Video
Skip Length and Inter-Starvation Distance as a Combined Metric to Assess the Quality of Transmitted Video Mohamed Hassan, Taha Landolsi, Husameldin Mukhtar, and Tamer Shanableh College of Engineering American
More informationAutomatic Rhythmic Notation from Single Voice Audio Sources
Automatic Rhythmic Notation from Single Voice Audio Sources Jack O Reilly, Shashwat Udit Introduction In this project we used machine learning technique to make estimations of rhythmic notation of a sung
More informationExploring Relationships between Audio Features and Emotion in Music
Exploring Relationships between Audio Features and Emotion in Music Cyril Laurier, *1 Olivier Lartillot, #2 Tuomas Eerola #3, Petri Toiviainen #4 * Music Technology Group, Universitat Pompeu Fabra, Barcelona,
More informationTopic 4. Single Pitch Detection
Topic 4 Single Pitch Detection What is pitch? A perceptual attribute, so subjective Only defined for (quasi) harmonic sounds Harmonic sounds are periodic, and the period is 1/F0. Can be reliably matched
More informationPOLYPHONIC INSTRUMENT RECOGNITION USING SPECTRAL CLUSTERING
POLYPHONIC INSTRUMENT RECOGNITION USING SPECTRAL CLUSTERING Luis Gustavo Martins Telecommunications and Multimedia Unit INESC Porto Porto, Portugal lmartins@inescporto.pt Juan José Burred Communication
More informationMUSICAL INSTRUMENT IDENTIFICATION BASED ON HARMONIC TEMPORAL TIMBRE FEATURES
MUSICAL INSTRUMENT IDENTIFICATION BASED ON HARMONIC TEMPORAL TIMBRE FEATURES Jun Wu, Yu Kitano, Stanislaw Andrzej Raczynski, Shigeki Miyabe, Takuya Nishimoto, Nobutaka Ono and Shigeki Sagayama The Graduate
More informationPitch. The perceptual correlate of frequency: the perceptual dimension along which sounds can be ordered from low to high.
Pitch The perceptual correlate of frequency: the perceptual dimension along which sounds can be ordered from low to high. 1 The bottom line Pitch perception involves the integration of spectral (place)
More informationCSC475 Music Information Retrieval
CSC475 Music Information Retrieval Monophonic pitch extraction George Tzanetakis University of Victoria 2014 G. Tzanetakis 1 / 32 Table of Contents I 1 Motivation and Terminology 2 Psychacoustics 3 F0
More informationA Categorical Approach for Recognizing Emotional Effects of Music
A Categorical Approach for Recognizing Emotional Effects of Music Mohsen Sahraei Ardakani 1 and Ehsan Arbabi School of Electrical and Computer Engineering, College of Engineering, University of Tehran,
More informationTowards Music Performer Recognition Using Timbre Features
Proceedings of the 3 rd International Conference of Students of Systematic Musicology, Cambridge, UK, September3-5, 00 Towards Music Performer Recognition Using Timbre Features Magdalena Chudy Centre for
More informationChord Classification of an Audio Signal using Artificial Neural Network
Chord Classification of an Audio Signal using Artificial Neural Network Ronesh Shrestha Student, Department of Electrical and Electronic Engineering, Kathmandu University, Dhulikhel, Nepal ---------------------------------------------------------------------***---------------------------------------------------------------------
More informationMOTIVATION AGENDA MUSIC, EMOTION, AND TIMBRE CHARACTERIZING THE EMOTION OF INDIVIDUAL PIANO AND OTHER MUSICAL INSTRUMENT SOUNDS
MOTIVATION Thank you YouTube! Why do composers spend tremendous effort for the right combination of musical instruments? CHARACTERIZING THE EMOTION OF INDIVIDUAL PIANO AND OTHER MUSICAL INSTRUMENT SOUNDS
More informationClassification of Musical Instruments sounds by Using MFCC and Timbral Audio Descriptors
Classification of Musical Instruments sounds by Using MFCC and Timbral Audio Descriptors Priyanka S. Jadhav M.E. (Computer Engineering) G. H. Raisoni College of Engg. & Mgmt. Wagholi, Pune, India E-mail:
More informationAutomatic Laughter Detection
Automatic Laughter Detection Mary Knox 1803707 knoxm@eecs.berkeley.edu December 1, 006 Abstract We built a system to automatically detect laughter from acoustic features of audio. To implement the system,
More informationIMPROVING RHYTHMIC SIMILARITY COMPUTATION BY BEAT HISTOGRAM TRANSFORMATIONS
1th International Society for Music Information Retrieval Conference (ISMIR 29) IMPROVING RHYTHMIC SIMILARITY COMPUTATION BY BEAT HISTOGRAM TRANSFORMATIONS Matthias Gruhne Bach Technology AS ghe@bachtechnology.com
More informationHUMAN PERCEPTION AND COMPUTER EXTRACTION OF MUSICAL BEAT STRENGTH
Proc. of the th Int. Conference on Digital Audio Effects (DAFx-), Hamburg, Germany, September -8, HUMAN PERCEPTION AND COMPUTER EXTRACTION OF MUSICAL BEAT STRENGTH George Tzanetakis, Georg Essl Computer
More informationEFFECTS OF REVERBERATION TIME AND SOUND SOURCE CHARACTERISTIC TO AUDITORY LOCALIZATION IN AN INDOOR SOUND FIELD. Chiung Yao Chen
ICSV14 Cairns Australia 9-12 July, 2007 EFFECTS OF REVERBERATION TIME AND SOUND SOURCE CHARACTERISTIC TO AUDITORY LOCALIZATION IN AN INDOOR SOUND FIELD Chiung Yao Chen School of Architecture and Urban
More informationA Parametric Autoregressive Model for the Extraction of Electric Network Frequency Fluctuations in Audio Forensic Authentication
Proceedings of the 3 rd International Conference on Control, Dynamic Systems, and Robotics (CDSR 16) Ottawa, Canada May 9 10, 2016 Paper No. 110 DOI: 10.11159/cdsr16.110 A Parametric Autoregressive Model
More informationSTRUCTURAL CHANGE ON MULTIPLE TIME SCALES AS A CORRELATE OF MUSICAL COMPLEXITY
STRUCTURAL CHANGE ON MULTIPLE TIME SCALES AS A CORRELATE OF MUSICAL COMPLEXITY Matthias Mauch Mark Levy Last.fm, Karen House, 1 11 Bache s Street, London, N1 6DL. United Kingdom. matthias@last.fm mark@last.fm
More informationSpeech and Speaker Recognition for the Command of an Industrial Robot
Speech and Speaker Recognition for the Command of an Industrial Robot CLAUDIA MOISA*, HELGA SILAGHI*, ANDREI SILAGHI** *Dept. of Electric Drives and Automation University of Oradea University Street, nr.
More informationAcoustic and musical foundations of the speech/song illusion
Acoustic and musical foundations of the speech/song illusion Adam Tierney, *1 Aniruddh Patel #2, Mara Breen^3 * Department of Psychological Sciences, Birkbeck, University of London, United Kingdom # Department
More informationDAT335 Music Perception and Cognition Cogswell Polytechnical College Spring Week 6 Class Notes
DAT335 Music Perception and Cognition Cogswell Polytechnical College Spring 2009 Week 6 Class Notes Pitch Perception Introduction Pitch may be described as that attribute of auditory sensation in terms
More informationAN ARTISTIC TECHNIQUE FOR AUDIO-TO-VIDEO TRANSLATION ON A MUSIC PERCEPTION STUDY
AN ARTISTIC TECHNIQUE FOR AUDIO-TO-VIDEO TRANSLATION ON A MUSIC PERCEPTION STUDY Eugene Mikyung Kim Department of Music Technology, Korea National University of Arts eugene@u.northwestern.edu ABSTRACT
More informationComposer Identification of Digital Audio Modeling Content Specific Features Through Markov Models
Composer Identification of Digital Audio Modeling Content Specific Features Through Markov Models Aric Bartle (abartle@stanford.edu) December 14, 2012 1 Background The field of composer recognition has
More informationA REAL-TIME SIGNAL PROCESSING FRAMEWORK OF MUSICAL EXPRESSIVE FEATURE EXTRACTION USING MATLAB
12th International Society for Music Information Retrieval Conference (ISMIR 2011) A REAL-TIME SIGNAL PROCESSING FRAMEWORK OF MUSICAL EXPRESSIVE FEATURE EXTRACTION USING MATLAB Ren Gang 1, Gregory Bocko
More informationHIT SONG SCIENCE IS NOT YET A SCIENCE
HIT SONG SCIENCE IS NOT YET A SCIENCE François Pachet Sony CSL pachet@csl.sony.fr Pierre Roy Sony CSL roy@csl.sony.fr ABSTRACT We describe a large-scale experiment aiming at validating the hypothesis that
More informationMusic Genre Classification
Music Genre Classification chunya25 Fall 2017 1 Introduction A genre is defined as a category of artistic composition, characterized by similarities in form, style, or subject matter. [1] Some researchers
More informationOutline. Why do we classify? Audio Classification
Outline Introduction Music Information Retrieval Classification Process Steps Pitch Histograms Multiple Pitch Detection Algorithm Musical Genre Classification Implementation Future Work Why do we classify
More informationLaboratory Assignment 3. Digital Music Synthesis: Beethoven s Fifth Symphony Using MATLAB
Laboratory Assignment 3 Digital Music Synthesis: Beethoven s Fifth Symphony Using MATLAB PURPOSE In this laboratory assignment, you will use MATLAB to synthesize the audio tones that make up a well-known
More informationMusic Information Retrieval with Temporal Features and Timbre
Music Information Retrieval with Temporal Features and Timbre Angelina A. Tzacheva and Keith J. Bell University of South Carolina Upstate, Department of Informatics 800 University Way, Spartanburg, SC
More informationA prototype system for rule-based expressive modifications of audio recordings
International Symposium on Performance Science ISBN 0-00-000000-0 / 000-0-00-000000-0 The Author 2007, Published by the AEC All rights reserved A prototype system for rule-based expressive modifications
More informationOn Human Capability and Acoustic Cues for Discriminating Singing and Speaking Voices
On Human Capability and Acoustic Cues for Discriminating Singing and Speaking Voices Yasunori Ohishi 1 Masataka Goto 3 Katunobu Itou 2 Kazuya Takeda 1 1 Graduate School of Information Science, Nagoya University,
More informationDERIVING A TIMBRE SPACE FOR THREE TYPES OF COMPLEX TONES VARYING IN SPECTRAL ROLL-OFF
DERIVING A TIMBRE SPACE FOR THREE TYPES OF COMPLEX TONES VARYING IN SPECTRAL ROLL-OFF William L. Martens 1, Mark Bassett 2 and Ella Manor 3 Faculty of Architecture, Design and Planning University of Sydney,
More informationAcoustic Scene Classification
Acoustic Scene Classification Marc-Christoph Gerasch Seminar Topics in Computer Music - Acoustic Scene Classification 6/24/2015 1 Outline Acoustic Scene Classification - definition History and state of
More informationLISTENERS RESPONSE TO STRING QUARTET PERFORMANCES RECORDED IN VIRTUAL ACOUSTICS
LISTENERS RESPONSE TO STRING QUARTET PERFORMANCES RECORDED IN VIRTUAL ACOUSTICS SONG HUI CHON 1, DOYUEN KO 2, SUNGYOUNG KIM 3 1 School of Music, Ohio State University, Columbus, Ohio, USA chon.21@osu.edu
More informationinter.noise 2000 The 29th International Congress and Exhibition on Noise Control Engineering August 2000, Nice, FRANCE
Copyright SFA - InterNoise 2000 1 inter.noise 2000 The 29th International Congress and Exhibition on Noise Control Engineering 27-30 August 2000, Nice, FRANCE I-INCE Classification: 6.1 INFLUENCE OF THE
More informationTOWARD AN INTELLIGENT EDITOR FOR JAZZ MUSIC
TOWARD AN INTELLIGENT EDITOR FOR JAZZ MUSIC G.TZANETAKIS, N.HU, AND R.B. DANNENBERG Computer Science Department, Carnegie Mellon University 5000 Forbes Avenue, Pittsburgh, PA 15213, USA E-mail: gtzan@cs.cmu.edu
More informationAn Examination of Foote s Self-Similarity Method
WINTER 2001 MUS 220D Units: 4 An Examination of Foote s Self-Similarity Method Unjung Nam The study is based on my dissertation proposal. Its purpose is to improve my understanding of the feature extractors
More informationMusical Instrument Identification Using Principal Component Analysis and Multi-Layered Perceptrons
Musical Instrument Identification Using Principal Component Analysis and Multi-Layered Perceptrons Róisín Loughran roisin.loughran@ul.ie Jacqueline Walker jacqueline.walker@ul.ie Michael O Neill University
More information